AI Applications

Place3D optimizes LiDAR placement for superior 3D scene understanding.

Robots using LLMs for task planning often make unsafe or wrong decisions due to LLM hallucination and ambiguity in instructions. This paper introduces ‘introspective planning,’ a novel method that us…

Stable closed-loop control in latent space is achieved using a novel Coupled Oscillator Network, offering efficient model-based control for complex nonlinear systems directly from image data.

EpoD, a novel dynamic graph learning model, significantly improves generalization via a self-prompted learning mechanism for environment inference and a structural causal model utilizing dynamic subgr…

Idiographic Personality Gaussian Process (IPGP) offers a novel measurement framework that captures both shared and individual-specific psychological traits, improving prediction accuracy and revealing…

AI pinpoints climate change impacts by identifying spatio-temporal extreme event drivers!

GEMCODE, a hybrid AI pipeline, automates co-crystal design for enhanced drug tabletability by combining deep generative models and evolutionary optimization, predicting numerous novel co-crystals.

Humanoid robots now walk in San Francisco zero-shot, thanks to a novel ’next token prediction’ approach trained on diverse sensorimotor data, enabling real-world generalization and data efficiency.

Boost AI predictions by using human judgment on algorithmically indistinguishable inputs!

High-Rank PCF-GAN uses a novel metric (HRPCFD) based on high-rank path development to learn filtration of stochastic processes, outperforming state-of-the-art methods in hypothesis testing and time-se…

HEALNet: a novel multimodal fusion network achieving state-of-the-art performance on biomedical survival analysis by effectively integrating heterogeneous data while handling missing modalities.

Robots can now dexterously grasp objects based on natural language commands thanks to DexGYS, a new language-guided dexterous grasp generation framework and dataset.

SEvo, a novel embedding update mechanism, directly injects graph structural information into recommendation embeddings, boosting performance significantly while avoiding the computational overhead of …

GOOSE: a novel framework using graph learning for efficient and interpretable numeric planning, outperforming existing methods in many benchmarks.

Graph Diffusion Transformer (Graph DiT) masters multi-conditional molecular generation by cleverly integrating property representations into a graph-dependent noise model, achieving superior performan…

GFNSeqEditor, a novel biological sequence editing algorithm, efficiently enhances desired properties while minimizing edits using generative flow networks, surpassing existing methods.

CMuST: a novel continuous multi-task spatiotemporal learning framework tackles urban data limitations by enabling cross-interactions and task-level cooperation for enhanced generalization and adaptabi…

ConStruct: Generating realistic graphs with guaranteed structural properties via constrained diffusion.

GeNSIT: a neural framework efficiently generates origin-destination matrices for agent-based models, outperforming existing methods in accuracy and scalability by directly operating on the discrete sp…

WeatherGFT generalizes weather forecasts to finer temporal scales using a physics-AI hybrid model, achieving state-of-the-art performance and 30-minute forecast capability with only hourly training da…